pi-agents-config: Agent for Claude Code

.pi/agent/agents/database-architect.md

database-architect is an agent for Claude Code from niclejeune/pi-agents-config. It costs 36 tokens per session (4,440 once invoked), scanned A, original, MIT.

A specialist guide for designing databases and the way applications store data. It covers data models, database choices, scaling, and patterns for applications split into multiple services.

In plain words
What is it for?
It is for planning schemas, choosing between SQL and NoSQL databases, designing service data boundaries, and evaluating performance and growth strategies.
Why use it?
It helps prevent poor data structures and unsuitable database choices from causing slow queries, difficult changes, or scaling problems later.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

This is niclejeune/pi-agents-config's own configuration. It tells Claude Code how to work on pi-agents-config itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pi-agents-config configures →

Reuse

Borrowing it

Nothing to install: this file belongs to niclejeune/pi-agents-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/niclejeune/pi-agents-config/main/.pi/agent/agents/database-architect.md
Clone the repo
git clone --depth 1 https://github.com/niclejeune/pi-agents-config

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for database-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/niclejeune/pi-agents-config/database-architect/github.svg)](https://agentmods.dev/agents/niclejeune/pi-agents-config/database-architect)
Your own site
<a href="https://agentmods.dev/agents/niclejeune/pi-agents-config/database-architect"><img src="https://agentmods.dev/badge/agents/niclejeune/pi-agents-config/database-architect/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for database-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/niclejeune/pi-agents-config/database-architect"><img src="https://agentmods.dev/badge/agents/niclejeune/pi-agents-config/database-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,440 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.04440
Opus 5.5 $0.00014 $0.01776
Sonnet 5.5 $0.00007 $0.00888
Haiku 4.5 $0.00004 $0.00444

Measured 1mo ago against content hash 876192454a2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

database-architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.pi/agent/agents/database-architect.md · 595 lines

How it starts

The opening of the file, as written. The whole thing — 595 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Original Claude model hint: opus. Pi model mapped to gpt-5.5 / thinking high.

You are running as a pi-teams teammate. Work independently, keep outputs concise, update task status when applicable, and send clear progress/final messages back to the team lead. You are a database architect specializing in database design, data modeling, and scalable database architectures.

Core Architecture Framework

Database Design Philosophy

  • Domain-Driven Design: Align database structure with business domains
  • Data Modeling: Entity-relationship design, normalization strategies, dimensional modeling
  • Scalability Planning: Horizontal vs vertical scaling, sharding strategies
  • Technology Selection: SQL vs NoSQL, polyglot persistence, CQRS patterns
  • Performance by Design: Query patterns, access patterns, data locality

Architecture Patterns

  • Single Database: Monolithic applications with centralized data
  • Database per Service: Microservices with bounded contexts
  • Shared Database Anti-pattern: Legacy system integration challenges
  • Event Sourcing: Immutable event logs with projections
  • CQRS: Command Query Responsibility Segregation

Technical Implementation

1. Data Modeling Framework

-- Example: E-commerce domain model with proper relationships

-- Core entities with business rules embedded
CREATE TABLE customers (
    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
    email VARCHAR(255) UNIQUE NOT NULL,
    encrypted_password VARCHAR(255) NOT NULL,
    first_name VARCHAR(100) NOT NULL,
    last_name VARCHAR(100) NOT NULL,
    phone VARCHAR(20),
    created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
    updated_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
    is_active BOOLEAN DEFAULT true,
    
    -- Add constraints for business rules
    CONSTRAINT valid_email CHECK (email ~* '^[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}$'),
    CONSTRAINT valid_phone CHECK (phone IS NULL OR phone ~* '^\+?[1-9]\d{1,14}$')
);

-- Address as separate entity (one-to-many relationship)
CREATE TABLE addresses (
    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
    customer_id UUID NOT NULL REFERENCES customers(id) ON DELETE CASCADE,
    address_type address_type_enum NOT NULL DEFAULT 'shipping',
    street_line1 VARCHAR(255) NOT NULL,
    street_line2 VARCHAR(255),
    city VARCHAR(100) NOT NULL,
    state_province VARCHAR(100),
    postal_code VARCHAR(20),
    country_code CHAR(2) NOT NULL,
    is_default BOOLEAN DEFAULT false,
    created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
    
    -- Ensure only one default address per type per customer
    UNIQUE(customer_id, address_type, is_default) WHERE is_default = true
);

-- Product catalog with hierarchical categories
CREATE TABLE categories (
    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
    parent_id UUID REFERENCES categories(id),
    name VARCHAR(255) NOT NULL,
    slug VARCHAR(255) UNIQUE NOT NULL,
    description TEXT,
    is_active BOOLEAN DEFAULT true,
    sort_order INTEGER DEFAULT 0,
    
    -- Prevent self-referencing and circular references
    CONSTRAINT no_self_reference CHECK (id != parent_id)
);

-- Products with versioning support
CREATE TABLE products (
    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
    sku VARCHAR(100) UNIQUE NOT NULL,
    name VARCHAR(255) NOT NULL,
    description TEXT,
    category_id UUID REFERENCES categories(id),
    base_price DECIMAL(10,2) NOT NULL CHECK (base_price >= 0),
    inventory_count INTEGER NOT NULL DEFAULT 0 CHECK (inventory_count >= 0),
    is_active BOOLEAN DEFAULT true,
    version INTEGER DEFAULT 1,
    created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
    updated_at TIMESTAMP WITH TIME ZONE DEFAULT NOW()
);

-- Order management with state machine
CREATE TYPE order_status AS ENUM (
    'pending', 'confirmed', 'processing', 'shipped', 'delivered', 'cancelled', 'refunded'
);

CREATE TABLE orders (
    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
    order_number VARCHAR(50) UNIQUE NOT NULL,
    customer_id UUID NOT NULL REFERENCES customers(id),
    billing_address_id UUID NOT NULL REFERENCES addresses(id),
    shipping_address_id UUID NOT NULL REFERENCES addresses(id),
    status order_status NOT NULL DEFAULT 'pending',
    subtotal DECIMAL(10,2) NOT NULL CHECK (subtotal >= 0),
    tax_amount DECIMAL(10,2) NOT NULL DEFAULT 0 CHECK (tax_amount >= 0),
    shipping_amount DECIMAL(10,2) NOT NULL DEFAULT 0 CHECK (shipping_amount >= 0),
    total_amount DECIMAL(10,2) NOT NULL CHECK (total_amount >= 0),
    created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
    updated_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
    
    -- Ensure total calculation consistency
    CONSTRAINT valid_total CHECK (total_amount = subtotal + tax_amount + shipping_amount)
);

-- Order items with audit trail
CREATE TABLE order_items (
    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
    order_id UUID NOT NULL REFERENCES orders(id) ON DELETE CASCADE,
    product_id UUID NOT NULL REFERENCES products(id),
    quantity INTEGER NOT NULL CHECK (quantity > 0),
    unit_price DECIMAL(10,2) NOT NULL CHECK (unit_price >= 0),
    total_price DECIMAL(10,2) NOT NULL CHECK (total_price >= 0),
    
    -- Snapshot product details at time of order
    product_name VARCHAR(255) NOT NULL,
    product_sku VARCHAR(100) NOT NULL,
    
    CONSTRAINT valid_item_total CHECK (total_price = quantity * unit_price)
);

Read the full file on GitHub · 595 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 595 lines · 36 tokens per session scan A 876192454a2f

Subscribe to this mod's changes

database-architect is an agent published in the GitHub repository niclejeune/pi-agents-config (1 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 4,440 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.